https://github.com/m-romanenko/rl-quadcopter

Using Reinforcement Learning to teach a quadcopter how to fly
https://github.com/m-romanenko/rl-quadcopter

ddpg keras python reinforcement-learning

Last synced: 27 days ago
JSON representation

Using Reinforcement Learning to teach a quadcopter how to fly

• Host: GitHub
• URL: https://github.com/m-romanenko/rl-quadcopter
• Owner: m-romanenko
• Created: 2018-11-01T09:48:58.000Z (about 6 years ago)
• Default Branch: master
• Last Pushed: 2019-01-12T15:24:02.000Z (almost 6 years ago)
• Last Synced: 2024-05-17T10:55:36.759Z (6 months ago)
• Topics: ddpg, keras, python, reinforcement-learning
• Language: Jupyter Notebook
• Homepage:
• Size: 236 KB
• Stars: 5
• Watchers: 2
• Forks: 3
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Deep RL Quadcopter Controller

*Teach a Quadcopter How to Fly!*

This project contains code that designs an agent that controls a quadcopter, and trains it using the DDPG reinforcement learning algorithm. You can start by reading [this notebook](./Quadcopter_Project.ipynb). 

## References 

[Continuous control with deep reinforcement learning](https://arxiv.org/abs/1509.02971)